All courses · Course overview · Lesson sequence
Skip to lesson textCourse reference
Guest-reading edition: see edition scope and limitations. The authoring-status notes in this document describe the original 17 October snapshot.
Generative AI and RAG: answer from evidence
The problem we solve
A fictional help desk has a handbook, older policies and questions written in language the handbook does not use. A fluent answer can cite the wrong version, omit a condition or invent a policy. This course builds an inspectable evidence workflow and explains what changes when a generator enters it.
By the end, a learner should be able to explain generation mechanisms and limits, preserve source identity through chunking, calculate retrieval signals, assemble bounded context, review claims and diagnose failures. The capstone is a reproducible argument about a declared policy on synthetic evidence, not a deployed assistant.
Prerequisites: Python functions, dictionaries, file handling and basic tests. Module 1 requires no vector mathematics; later lessons derive the small calculations they use. Python for AI and Data is a suitable entry route. Deep Learning Foundations is useful background, but no neural training background is required. No FastAPI, cloud account, paid service or model credential is required.
Suggested pace: 24–30 hours including independent exercises and capstone revision, as a design estimate rather than measured learner completion time. All ten lessons and practice/solutions are authored. Predict a result, run the named experiment, explain its output, then attempt practice before reading solutions.
| Module and full lesson | What you will demonstrate | Independent practice | Explained solutions |
|---|---|---|---|
| 1. Start with an answer contract | Preserve conditions, separate evidence from drafting and diagnose two failure types | Practice 1 | Solutions 1 |
| 2. Understand what a generator does | Count/train/decode a toy LM; calculate temperature/attention arithmetic; distinguish words from neural tokens | Practice 2 | Solutions 2 |
| 3. Build a source collection | Trace exact spans; compare windows/paragraphs; expose oversized atoms and version ambiguity | Practice 3 | Solutions 3 |
| 4. Explain a lexical baseline | Derive smoothed TF-IDF/cosine; check arithmetic; inspect cutoff/unknown-term failures | Practice 4 | Solutions 4 |
| 5. Compare semantic/hybrid/rerank concepts | Distinguish learned representations from manual vectors; calculate RRF; bound an exact-term filter's claim | Practice 5 | Solutions 5 |
| 6. Select context | Compare ranking/packet coverage; budget whole quotes; report duplicates/conflicts | Practice 6 | Solutions 6 |
| 7. Draft supported claims | Inspect a source-bound authored template; distinguish support, intent mapping and identity | Practice 7 | Solutions 7 |
| 8. Evaluate the whole path | Separate denominators; aggregate manual labels; design a less-biased comparison | Practice 8 | Solutions 8 |
| 9. Trace failures and state limits | Reproduce budget/source-change traces; keep source instructions as data; bound a handoff | Practice 9 | Solutions 9 |
| 10. Defend the capstone | Complete a selector hook; freeze inputs; compare policies; preserve hard cases and defend a conclusion | Capstone task | Capstone solutions |
Actual execution and assessment boundary
The project performs lexical retrieval, exact text chunking, whole-quote selection and authored template rendering. It also runs a count-based toy LM and manual-vector simulations. It does not run a neural LLM, learned encoder, learned reranker or model judge. Optional future model-study designs are not executed evidence. All supplied questions were visible during development.
The capstone self-review gives equal weight to source/provenance correctness, retrieval/context reasoning, evaluation design and clarity about claims/limits. Polished prose cannot compensate for fabricated execution, concealed unsupported claims or missing conditions. The rubric is formative local feedback, not approved platform pass criteria or a certificate policy. No learner completion or credit logic is integrated.
Scope alongside other Aabha courses
This course builds on document checking in Everyday AI and knowledge-pack design in Codeless Assistants. It does not repeat the FastAPI Equipment Rental API, implement authentication, manage agent tools or teach a deployment pipeline. Tool/action orchestration belongs to Agentic Workflow Engineering; ongoing operations/release monitoring belongs to LLMOps. Scope handoffs do not imply those neighboring packages or any production release are complete.